smids_3x_beit_base_adamax_00001_fold1

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.8301
• Accuracy: 0.9098

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2349	1.0	376	0.2964	0.8848
0.2022	2.0	752	0.2944	0.8932
0.1706	3.0	1128	0.2893	0.8965
0.0767	4.0	1504	0.3105	0.9015
0.0646	5.0	1880	0.3471	0.9015
0.0505	6.0	2256	0.3777	0.9015
0.0505	7.0	2632	0.4146	0.9115
0.0821	8.0	3008	0.4739	0.9115
0.0331	9.0	3384	0.5133	0.9082
0.0097	10.0	3760	0.5124	0.9065
0.0367	11.0	4136	0.5327	0.9098
0.0236	12.0	4512	0.6380	0.8881
0.0306	13.0	4888	0.6670	0.9015
0.0605	14.0	5264	0.6155	0.9048
0.0306	15.0	5640	0.6494	0.9082
0.0004	16.0	6016	0.6896	0.9098
0.007	17.0	6392	0.7511	0.9082
0.015	18.0	6768	0.7380	0.9015
0.0089	19.0	7144	0.7967	0.8982
0.0001	20.0	7520	0.7574	0.9082
0.002	21.0	7896	0.7435	0.9098
0.0015	22.0	8272	0.7583	0.9115
0.0335	23.0	8648	0.7482	0.9132
0.0006	24.0	9024	0.7814	0.9098
0.0164	25.0	9400	0.7970	0.9065
0.0087	26.0	9776	0.7792	0.8948
0.0002	27.0	10152	0.7650	0.9032
0.0006	28.0	10528	0.7540	0.9115
0.0065	29.0	10904	0.7789	0.9048
0.0014	30.0	11280	0.8591	0.9015
0.0121	31.0	11656	0.7783	0.9149
0.0002	32.0	12032	0.7672	0.9132
0.0016	33.0	12408	0.7720	0.9132
0.0107	34.0	12784	0.7941	0.9132
0.0018	35.0	13160	0.8228	0.9132
0.0008	36.0	13536	0.8321	0.9082
0.0001	37.0	13912	0.8043	0.9149
0.0	38.0	14288	0.8040	0.9115
0.0001	39.0	14664	0.8027	0.9149
0.0057	40.0	15040	0.8085	0.9115
0.0	41.0	15416	0.8221	0.9082
0.0001	42.0	15792	0.8229	0.9115
0.0	43.0	16168	0.8358	0.9065
0.0001	44.0	16544	0.8054	0.9132
0.0104	45.0	16920	0.8285	0.9065
0.0009	46.0	17296	0.8368	0.9098
0.0003	47.0	17672	0.8285	0.9132
0.0028	48.0	18048	0.8334	0.9115
0.0156	49.0	18424	0.8298	0.9098
0.0004	50.0	18800	0.8301	0.9098

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2